© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Olmo-3-1125-32B
    5. 32-RES-BATCHTOPK-131K
    7. 29311
    Prev
    Next
    INDEX
    Explanations

    restrict or limit access

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    bcywinski/Olmo-3-32B-Base-SAE/saes_allenai_Olmo-3-1125-32B_batch_top_k/resid_post_layer_32
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     exclus
    -0.09
     distinctions
    -0.09
     Cafe
    -0.09
     ail
    -0.09
     trouble
    -0.09
     exter
    -0.08
     rejection
    -0.08
    udad
    -0.08
    ungan
    -0.07
     tur
    -0.07
    POSITIVE LOGITS
     access
    0.22
     freedom
    0.22
     movement
    0.21
     freedoms
    0.20
     mobility
    0.20
     severely
    0.18
     growth
    0.18
     ability
    0.18
     creativity
    0.18
     movements
    0.17
    Activations Density 0.310%

    No Known Activations